In [29]:
import pandas as pd
df = pd.read_csv('Reviews.csv.zip')
df.head()
Out[29]:
Id ProductId UserId ProfileName HelpfulnessNumerator HelpfulnessDenominator Score Time Summary Text
0 1 B001E4KFG0 A3SGXH7AUHU8GW delmartian 1 1 5 1303862400 Good Quality Dog Food I have bought several of the Vitality canned d...
1 2 B00813GRG4 A1D87F6ZCVE5NK dll pa 0 0 1 1346976000 Not as Advertised Product arrived labeled as Jumbo Salted Peanut...
2 3 B000LQOCH0 ABXLMWJIXXAIN Natalia Corres "Natalia Corres" 1 1 4 1219017600 "Delight" says it all This is a confection that has been around a fe...
3 4 B000UA0QIQ A395BORC6FGVXV Karl 3 3 2 1307923200 Cough Medicine If you are looking for the secret ingredient i...
4 5 B006K2ZZ7K A1UQRSCLF8GW1T Michael D. Bigham "M. Wassir" 0 0 5 1350777600 Great taffy Great taffy at a great price. There was a wid...
In [30]:
# Imports
import matplotlib.pyplot as plt
import seaborn as sns
color = sns.color_palette()
%matplotlib inline
import plotly.offline as py
py.init_notebook_mode(connected=True)
import plotly.graph_objs as go
import plotly.tools as tls
import plotly.express as px
# Product Scores
fig = px.histogram(df, x="Score")
fig.update_traces(marker_color="turquoise",marker_line_color='rgb(8,48,107)',
                  marker_line_width=1.5)
fig.update_layout(title_text='Product Score')
fig.show()
In [14]:
from wordcloud import WordCloud, STOPWORDS
import matplotlib.pyplot as plt

# Create stopword list:
stopwords = set(STOPWORDS)
stopwords.update(["br", "href"])
textt = " ".join(review for review in df.Text)
wordcloud = WordCloud(stopwords=stopwords).generate(textt)
plt.imshow(wordcloud, interpolation='bilinear')
plt.axis("off")
plt.savefig('wordcloud11.png')
plt.show() 
In [31]:
# assign reviews with score > 3 as positive sentiment
# score < 3 negative sentiment
# remove score = 3
df = df[df['Score'] != 3]
df['sentiment'] = df['Score'].apply(lambda rating : +1 if rating > 3 else -1)
In [23]:
# split df - positive and negative sentiment:
positive = df[df['sentiment'] == 1]
negative = df[df['sentiment'] == -1]
In [32]:
stopwords = set(STOPWORDS)
stopwords.update(["br", "href","good","great"]) 
## good and great removed because they were included in negative sentiment
pos = " ".join(review for review in positive.Summary)
wordcloud2 = WordCloud(stopwords=stopwords).generate(pos)
plt.imshow(wordcloud2, interpolation='bilinear')
plt.axis("off")
plt.show()
In [35]:
neg = " ".join(str(review) for review in negative.Summary)
wordcloud3 = WordCloud(stopwords=stopwords).generate(neg)

plt.imshow(wordcloud3, interpolation='bilinear')
plt.axis("off")
plt.savefig('wordcloud33.png')
plt.show()
In [36]:
df['sentimentt'] = df['sentiment'].replace({-1 : 'negative'})
df['sentimentt'] = df['sentimentt'].replace({1 : 'positive'})
fig = px.histogram(df, x="sentimentt")
fig.update_traces(marker_color="indianred",marker_line_color='rgb(8,48,107)',
                  marker_line_width=1.5)
fig.update_layout(title_text='Product Sentiment')
fig.show()
In [40]:
def remove_punctuation(text):
    final = "".join(u for u in text if u not in ("?", ".", ";", ":",  "!",'"'))
    return final
df['Text'] = df['Text'].apply(remove_punctuation)
df = df.dropna(subset=['Summary'])
df['Summary'] = df['Summary'].apply(remove_punctuation)
In [39]:
dfNew = df[['Summary','sentiment']]
dfNew.head()
Out[39]:
Summary sentiment
0 Good Quality Dog Food 1
1 Not as Advertised -1
2 Delight says it all 1
3 Cough Medicine -1
4 Great taffy 1
In [43]:
# random split train and test data
import numpy as np
index = df.index
df['random_number'] = np.random.randn(len(index))
train = df[df['random_number'] <= 0.8]
test = df[df['random_number'] > 0.8]
In [44]:
# count vectorizer:
from sklearn.feature_extraction.text import CountVectorizer
vectorizer = CountVectorizer(token_pattern=r'\b\w+\b')
train_matrix = vectorizer.fit_transform(train['Summary'])
test_matrix = vectorizer.transform(test['Summary'])
In [45]:
# Logistic Regression
from sklearn.linear_model import LogisticRegression
lr = LogisticRegression()
In [46]:
X_train = train_matrix
X_test = test_matrix
y_train = train['sentiment']
y_test = test['sentiment']
In [47]:
lr.fit(X_train,y_train)
C:\Users\admin\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning:

lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression

Out[47]:
LogisticRegression()
In [48]:
predictions = lr.predict(X_test)
In [49]:
# find accuracy, precision, recall:
from sklearn.metrics import confusion_matrix,classification_report
new = np.asarray(y_test)
confusion_matrix(predictions,y_test)
Out[49]:
array([[11486,  2402],
       [ 5962, 91573]], dtype=int64)
In [50]:
print(classification_report(predictions,y_test))
              precision    recall  f1-score   support

          -1       0.66      0.83      0.73     13888
           1       0.97      0.94      0.96     97535

    accuracy                           0.92    111423
   macro avg       0.82      0.88      0.84    111423
weighted avg       0.94      0.92      0.93    111423

In [ ]: